{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:JTN3EYTTL34EYEIKEPMHTTJRZZ","short_pith_number":"pith:JTN3EYTT","canonical_record":{"source":{"id":"2505.12182","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-18T00:47:21Z","cross_cats_sorted":[],"title_canon_sha256":"b437701cb8c023749d93cec48e8e9dad071af62f662c8e395bb8a108e5982c64","abstract_canon_sha256":"b3cc4095c33b93eae96734ee2f9d6c59111ddc101544cd9cc7aad0a17e5e6261"},"schema_version":"1.0"},"canonical_sha256":"4cdbb262735ef84c110a23d879cd31ce4df06e5aaa814b8e5eebc8b5002d3d0f","source":{"kind":"arxiv","id":"2505.12182","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.12182","created_at":"2026-07-05T11:33:23Z"},{"alias_kind":"arxiv_version","alias_value":"2505.12182v3","created_at":"2026-07-05T11:33:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.12182","created_at":"2026-07-05T11:33:23Z"},{"alias_kind":"pith_short_12","alias_value":"JTN3EYTTL34E","created_at":"2026-07-05T11:33:23Z"},{"alias_kind":"pith_short_16","alias_value":"JTN3EYTTL34EYEIK","created_at":"2026-07-05T11:33:23Z"},{"alias_kind":"pith_short_8","alias_value":"JTN3EYTT","created_at":"2026-07-05T11:33:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:JTN3EYTTL34EYEIKEPMHTTJRZZ","target":"record","payload":{"canonical_record":{"source":{"id":"2505.12182","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-18T00:47:21Z","cross_cats_sorted":[],"title_canon_sha256":"b437701cb8c023749d93cec48e8e9dad071af62f662c8e395bb8a108e5982c64","abstract_canon_sha256":"b3cc4095c33b93eae96734ee2f9d6c59111ddc101544cd9cc7aad0a17e5e6261"},"schema_version":"1.0"},"canonical_sha256":"4cdbb262735ef84c110a23d879cd31ce4df06e5aaa814b8e5eebc8b5002d3d0f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:33:23.809983Z","signature_b64":"Dm2uo39uSt/Pho2fE6rDzAxaebsxvY/Tfb32g0WIsq4v0pzurofjjshja88+cfq5HMt1nXVcRZm4Fzgud5eGCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4cdbb262735ef84c110a23d879cd31ce4df06e5aaa814b8e5eebc8b5002d3d0f","last_reissued_at":"2026-07-05T11:33:23.809496Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:33:23.809496Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.12182","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:33:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mWwx0WSfbBUe2J4d5mlJCAev6I8kege8WzFA1e/1T6UtItmX8DQc/k/ZYwICIrIZ0lBZ0cYTqpBOzQljOxpwCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T05:49:49.365745Z"},"content_sha256":"000131a9139743f179d6b3e884fa7088820966a0a2c19d7fd29210fccfdb4109","schema_version":"1.0","event_id":"sha256:000131a9139743f179d6b3e884fa7088820966a0a2c19d7fd29210fccfdb4109"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:JTN3EYTTL34EYEIKEPMHTTJRZZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Truth Neurons","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Haohang Li, Jordan W. Suchow, Yangyang Yu, Yupeng Cao, Zining Zhu","submitted_at":"2025-05-18T00:47:21Z","abstract_excerpt":"Despite their remarkable success and deployment across diverse workflows, language models sometimes produce untruthful responses. Our limited understanding of how truthfulness is mechanistically encoded within these models jeopardizes their reliability and safety. In this paper, we propose a method for identifying representations of truthfulness at the neuron level. We show that language models contain truth neurons, which encode truthfulness in a subject-agnostic manner. Experiments conducted across models of varying scales validate the existence of truth neurons, confirming that the encoding"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.12182","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2505.12182/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:33:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1MVt1ioiBaDH2Zs3DwpDq3bI6hSe809Fy6WCeTl8jIpBIbDh2xx/E+6LZbc8y7BrG6xZjzosur/L7S0L524uAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T05:49:49.366265Z"},"content_sha256":"fc71f012d8cb65a5c8d1d0a13f3e8d2add8e0661a830624ddf718880e05d048e","schema_version":"1.0","event_id":"sha256:fc71f012d8cb65a5c8d1d0a13f3e8d2add8e0661a830624ddf718880e05d048e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JTN3EYTTL34EYEIKEPMHTTJRZZ/bundle.json","state_url":"https://pith.science/pith/JTN3EYTTL34EYEIKEPMHTTJRZZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JTN3EYTTL34EYEIKEPMHTTJRZZ/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-04T05:49:49Z","links":{"resolver":"https://pith.science/pith/JTN3EYTTL34EYEIKEPMHTTJRZZ","bundle":"https://pith.science/pith/JTN3EYTTL34EYEIKEPMHTTJRZZ/bundle.json","state":"https://pith.science/pith/JTN3EYTTL34EYEIKEPMHTTJRZZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JTN3EYTTL34EYEIKEPMHTTJRZZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:JTN3EYTTL34EYEIKEPMHTTJRZZ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"b3cc4095c33b93eae96734ee2f9d6c59111ddc101544cd9cc7aad0a17e5e6261","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-18T00:47:21Z","title_canon_sha256":"b437701cb8c023749d93cec48e8e9dad071af62f662c8e395bb8a108e5982c64"},"schema_version":"1.0","source":{"id":"2505.12182","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.12182","created_at":"2026-07-05T11:33:23Z"},{"alias_kind":"arxiv_version","alias_value":"2505.12182v3","created_at":"2026-07-05T11:33:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.12182","created_at":"2026-07-05T11:33:23Z"},{"alias_kind":"pith_short_12","alias_value":"JTN3EYTTL34E","created_at":"2026-07-05T11:33:23Z"},{"alias_kind":"pith_short_16","alias_value":"JTN3EYTTL34EYEIK","created_at":"2026-07-05T11:33:23Z"},{"alias_kind":"pith_short_8","alias_value":"JTN3EYTT","created_at":"2026-07-05T11:33:23Z"}],"graph_snapshots":[{"event_id":"sha256:fc71f012d8cb65a5c8d1d0a13f3e8d2add8e0661a830624ddf718880e05d048e","target":"graph","created_at":"2026-07-05T11:33:23Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2505.12182/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite their remarkable success and deployment across diverse workflows, language models sometimes produce untruthful responses. Our limited understanding of how truthfulness is mechanistically encoded within these models jeopardizes their reliability and safety. In this paper, we propose a method for identifying representations of truthfulness at the neuron level. We show that language models contain truth neurons, which encode truthfulness in a subject-agnostic manner. Experiments conducted across models of varying scales validate the existence of truth neurons, confirming that the encoding","authors_text":"Haohang Li, Jordan W. Suchow, Yangyang Yu, Yupeng Cao, Zining Zhu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-18T00:47:21Z","title":"Truth Neurons"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.12182","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:000131a9139743f179d6b3e884fa7088820966a0a2c19d7fd29210fccfdb4109","target":"record","created_at":"2026-07-05T11:33:23Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"b3cc4095c33b93eae96734ee2f9d6c59111ddc101544cd9cc7aad0a17e5e6261","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-18T00:47:21Z","title_canon_sha256":"b437701cb8c023749d93cec48e8e9dad071af62f662c8e395bb8a108e5982c64"},"schema_version":"1.0","source":{"id":"2505.12182","kind":"arxiv","version":3}},"canonical_sha256":"4cdbb262735ef84c110a23d879cd31ce4df06e5aaa814b8e5eebc8b5002d3d0f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4cdbb262735ef84c110a23d879cd31ce4df06e5aaa814b8e5eebc8b5002d3d0f","first_computed_at":"2026-07-05T11:33:23.809496Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:33:23.809496Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Dm2uo39uSt/Pho2fE6rDzAxaebsxvY/Tfb32g0WIsq4v0pzurofjjshja88+cfq5HMt1nXVcRZm4Fzgud5eGCA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:33:23.809983Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.12182","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:000131a9139743f179d6b3e884fa7088820966a0a2c19d7fd29210fccfdb4109","sha256:fc71f012d8cb65a5c8d1d0a13f3e8d2add8e0661a830624ddf718880e05d048e"],"state_sha256":"5e17bee29040e0171f95e1faa7f044db649b183828f8f07eeb196acfe6fb468a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vkY2DKzmC7wioq9233nRCmi2HhXsfkOtjiH7OLsG2y0l+R8aqVPxTtgu1rqPcb6CflSYXTfSngKxoClNHBSKBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T05:49:49.371280Z","bundle_sha256":"7018a22de729b322cb3bf1fa7ebdd1bd52314e9543672d97a4c26e195ca2b7d1"}}